Midv-578 May 2026

Developed as part of the broader series by researchers at the Institute for Information Transmission Problems and Moscow Institute of Physics and Technology, this dataset addresses the growing need for robust AI models capable of processing identity documents in uncontrolled, real-world environments. The Evolution of the MIDV Datasets

Banks and digital services use models trained on MIDV-578 to verify identities via smartphone cameras, ensuring that the system can read a driver's license from a remote region just as easily as a local passport. MIDV-578

It covers document formats from nearly every continent, ensuring that OCR (Optical Character Recognition) models trained on it are not biased toward a specific country's design or alphabet. Developed as part of the broader series by

Before reading text, a system must "find" the document in a video frame. MIDV-578 provides the ground truth (exact coordinates) needed to train these detection models. Before reading text, a system must "find" the

The dataset includes common mobile capture artifacts such as: Motion Blur: Caused by unsteady hands.